We introduce the Pontryagin-Guided Direct Policy Optimization (PG-DPO) framework for high-dimensional continuous-time portfolio choice. Our approach combines Pontryagin's Maximum Principle (PMP) with backpropagation through time (BPTT) to directly inform neural network-based policy learning, enabling accurate recovery of both myopic and intertemporal hedging demands--an aspect often missed by existing methods. Building on this, we develop the Projected PG-DPO (P-PGDPO) variant, which achieves nearoptimal policies with substantially improved efficiency. P-PGDPO leverages rapidly stabilizing costate estimates from BPTT and analytically projects them onto PMP's first-order conditions, reducing training overhead while improving precision. Numerical experiments show that PG-DPO matches or exceeds the accuracy of Deep BSDE, while P-PGDPO delivers significantly higher precision and scalability. By explicitly incorporating time-to-maturity, our framework naturally applies to finite-horizon problems and captures horizon-dependent effects, with the long-horizon case emerging as a stationary special case.
In this article, we study optimal investment and consumption in an incomplete stochastic factor model for a power utility investor on the infinite horizon. When the state space of the stochastic factor is finite, we give a complete characterisation of the well-posedness of the problem, and provide an efficient numerical algorithm for computing the value function. When the state space is a (possibly infinite) open interval and the stochastic factor is represented by an Itô diffusion, we develop a general theory of sub- and supersolutions for second-order ordinary differential equations on open domains without boundary values to prove existence of the solution to the Hamilton-Jacobi-Bellman (HJB) equation along with explicit bounds for the solution. By characterising the asymptotic behaviour of the solution, we are also able to provide rigorous verification arguments for various models, including -- for the first time -- the Heston model. Finally, we link the discrete and continuous setting and show that that the value function in the diffusion setting can be approximated very efficiently through a fast discretisation scheme.
The gas fee, paid for inclusion in the blockchain, is analyzed in two parts. First, we consider how effort in terms of resources required to process and store a transaction turns into a gas limit, which, through a fee, comprised of the base and priority fee in the current version of Ethereum, is converted into the cost paid by the user. We adhere closely to the Ethereum protocol to simplify the analysis and to constrain the design choices when considering multidimensional gas. Second, we assume that the gas price is given deus ex machina by a fractional Ornstein-Uhlenbeck process and evaluate various derivatives. These contracts can, for example, mitigate gas cost volatility. The ability to price and trade forwards besides the existing spot inclusion into the blockchain could enable users to hedge against future cost fluctuations. Overall, this paper offers a comprehensive analysis of gas fee dynamics on the Ethereum blockchain, integrating supply-side constraints with demand-side modelling to enhance the predictability and stability of transaction costs.
The measure of portfolio risk is an important input of the Markowitz framework. In this study, we explored various methods to obtain a robust covariance estimators that are less susceptible to financial data noise. We evaluated the performance of large-cap portfolio using various forms of Ledoit Shrinkage Covariance and Robust Gerber Covariance matrix during the period of 2012 to 2022. Out-of-sample performance indicates that robust covariance estimators can outperform the market capitalization-weighted benchmark portfolio, particularly during bull markets. The Gerber covariance with Mean-Absolute-Deviation (MAD) emerged as the top performer. However, robust estimators do not manage tail risk well under extreme market conditions, for example, Covid-19 period. When we aim to control for tail risk, we should add constraint on Conditional Value-at-Risk (CVaR) to make more conservative decision on risk exposure. Additionally, we incorporated unsupervised clustering algorithm K-means to the optimization algorithm (i.e. Nested Clustering Optimization, NCO). It not only helps mitigate numerical instability of the optimization algorithm, but also contributes to lower drawdown as well.
In quantitative finance, machine learning methods are essential for alpha generation. This study introduces a new approach that combines Hidden Markov Models (HMM) and neural networks, integrated with Black-Litterman portfolio optimization. During the COVID period (2019-2022), this dual-model approach achieved a 83% return with a Sharpe ratio of 0.77. It incorporates two risk models to enhance risk management, showing efficiency during volatile periods. The methodology was implemented on the QuantConnect platform, which was chosen for its robust framework and experimental reproducibility. The system, which predicts future price movements, includes a three-year warm-up to ensure proper algorithm function. It targets highly liquid, large-cap energy stocks to ensure stable and predictable performance while also considering broker payments. The dual-model alpha system utilizes log returns to select the optimal state based on the historical performance. It combines state predictions with neural network outputs, which are based on historical data, to generate trading signals. This study examined the architecture of the trading system, data pre-processing, training, and performance. The full code and backtesting data are available under the QuantConnect terms: https://github.com/tiagomonteiro0715/AI-Powered-Energy-Algorithmic-Trading-Integrating-Hidden-Markov-Models-with-Neural-Networks
Traditional methods employed in matrix volatility forecasting often overlook the inherent Riemannian manifold structure of symmetric positive definite matrices, treating them as elements of Euclidean space, which can lead to suboptimal predictive performance. Moreover, they often struggle to handle high-dimensional matrices. In this paper, we propose a novel approach for forecasting realized covariance matrices of asset returns using a Riemannian-geometry-aware deep learning framework. In this way, we account for the geometric properties of the covariance matrices, including possible non-linear dynamics and efficient handling of high-dimensionality. Moreover, building upon a Fréchet sample mean of realized covariance matrices, we are able to extend the HAR model to the matrix-variate. We demonstrate the efficacy of our approach using daily realized covariance matrices for the 50 most capitalized companies in the S&P 500 index, showing that our method outperforms traditional approaches in terms of predictive accuracy.
This is a review about financial dependencies which merges efforts in econophysics and financial economics during the last few years. We focus on the most relevant contributions to the analysis of asset markets' dependencies, especially correlational studies, which in our opinion are beneficial for researchers in both fields. In econophysics, these dependencies can be modeled to describe financial markets as evolving complex networks. In particular we show that a useful way to describe dependencies is by means of information filtering networks that are able to retrieve relevant and meaningful information in complex financial data sets. In financial economics these dependencies can describe asset comovement and spill-overs. In particular, several models are presented that show how network and factor model approaches are related to modeling of multivariate volatility and asset returns respectively. Finally, we sketch out how these studies can inspire future research and how they contribute to support researchers in both fields to find a better and a stronger common language.
Radu Burlacu, Patrice Fontaine, Sonia Jimenez-Garcès
We use the Grossman \& Stiglitz (1980) framework to build a reference portfolio for uninformed investors and employ this portfolio to assess the performance of actively managed equity mutual funds. We propose an empirical methodology to construct this reference portfolio using the information on prices and supply. We show that mutual funds provide, on average, an insignificant alpha of 23 basis points per year when considering this portfolio as a reference. With the stock market index as a proxy for the market portfolio, the average fund alpha is negative and highly significant, --128 basis points per year. The results are robust when considering various subsets of funds based on their characteristics and their degree of selectivity. In line with rational expectations equilibrium models considering asymmetrically informed investors and partially revealing equilibrium prices, our study supports that active management adds value for uniformed investors.
Machine Learning (ML) has been embraced as a powerful tool by the financial industry, with notable applications spreading in various domains including investment management. In this work, we propose a full-cycle data-driven investment robo-advising framework, consisting of two ML agents. The first agent, an inverse portfolio optimization agent, infers an investor's risk preference and expected return directly from historical allocation data using online inverse optimization. The second agent, a deep reinforcement learning (RL) agent, aggregates the inferred sequence of expected returns to formulate a new multi-period mean-variance portfolio optimization problem that can be solved using deep RL approaches. The proposed investment pipeline is applied on real market data from April 1, 2016 to February 1, 2021 and has shown to consistently outperform the S&P 500 benchmark portfolio that represents the aggregate market optimal allocation. The outperformance may be attributed to the the multi-period planning (versus single-period planning) and the data-driven RL approach (versus classical estimation approach).
In this article we consider the optimal investment-consumption problem for an agent with preferences governed by Epstein-Zin stochastic differential utility who invests in a constant-parameter Black-Scholes-Merton market. The paper has three main goals: first, to provide a detailed introduction to infinite-horizon Epstein-Zin stochastic differential utility, including a discussion of which parameter combinations lead to a well-formulated problem; second, to prove existence and uniqueness of infinite horizon Epstein-Zin stochastic differential utility under a restriction on the parameters governing the agent's risk aversion and temporal variance aversion; and third, to provide a verification argument for the candidate optimal solution to the investment-consumption problem among all admissible consumption streams. To achieve these goals, we introduce a slightly different formulation of Epstein-Zin stochastic differential utility to that which is traditionally used in the literature. This formulation highlights the necessity and appropriateness of certain restrictions on the parameters governing the stochastic differential utility function.
We propose a general family of piecewise hyperbolic absolute risk aversion (PHARA) utilities, including many classic and non-standard utilities as examples. A typical application is the composition of a HARA preference and a piecewise linear payoff in asset allocation. We derive a unified closed-form formula of the optimal portfolio, which is a four-term division. The formula has clear economic meanings, reflecting the behavior of risk aversion, risk seeking, loss aversion and first-order risk aversion. We conduct a general asymptotic analysis to the optimal portfolio, which directly serves as an analytical tool for financial analysis. We compare this PHARA portfolio with those of other utility families both analytically and numerically. One main finding is that risk-taking behaviors are greatly increased by non-concavity and reduced by non-differentiability of the PHARA utility. Finally, we use financial data to test the performance of the PHARA portfolio in the market.
We consider the problem of maximizing the asymptotic growth rate of an investor under drift uncertainty in the setting of stochastic portfolio theory (SPT). As in the work of Kardaras and Robertson we take as inputs (i) a Markovian volatility matrix $c(x)$ and (ii) an invariant density $p(x)$ for the market weights, but we additionally impose long-only constraints on the investor. Our principal contribution is proving a uniqueness and existence result for the class of concave functionally generated portfolios and developing a finite dimensional approximation, which can be used to numerically find the optimum. In addition to the general results outlined above, we propose the use of a broad class of models for the volatility matrix $c(x)$, which can be calibrated to data and, under which, we obtain explicit formulas of the optimal unconstrained portfolio for any invariant density.
The purpose of this paper is to introduce a new growth adjusted price-earnings measure (GA-P/E) and assess its efficacy as measure of value and predictor of future stock returns. Taking inspiration from the interpretation of the traditional price-earnings ratio as a period of time, the new measure computes the requisite payback period whilst accounting for earnings growth. Having derived the measure, we outline a number of its properties before conducting an extensive empirical study utilising a sorted portfolio methodology. We find that the returns of the low GA-P/E stocks exceed those of the high GA-P/E stocks, both in an absolute sense and also on a risk-adjusted basis. Furthermore, the returns from the low GA-P/E porfolio was found to exceed those of the value portfolio arising from a P/E sort on the same pool of stocks. Finally, the returns of our GA-P/E sorted porfolios were subjected to analysis by conducting regressions against the standard Fama and French risk factors.